© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15167
    Prev
    Next
    INDEX
    Explanations

    `<link rel="stylesheet"`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hd
    0.19
     hd
    0.19
     DAT
    0.19
    ('<
    0.19
    টার
    0.18
    Johannes
    0.18
    AudioManager
    0.18
     leveraged
    0.18
    hdf
    0.18
    Columbus
    0.18
    POSITIVE LOGITS
     outfile
    0.25
     Zweiten
    0.24
     pra
    0.23
     Upload
    0.22
     ringan
    0.22
     doctrine
    0.22
    doctrine
    0.21
    ಂ
    0.21
    elson
    0.21
    Unauthorized
    0.21
    Activations Density 0.000%

    No Known Activations